Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

Dataset: 80% C4 (Web Text) and 20% Python Code

Neuron 1852 in Layer 10

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 1.8269. Min Range: -1.8269

Max Act: 1.8269. Min Act: -0.0000

Data Index: 856172 (C4 (Web Text))

Max Activating Token Index: 877

Text #1

Max Range: 1.8269. Min Range: -1.8269

Max Act: 1.5110. Min Act: -0.0000

Data Index: 1334046 (C4 (Web Text))

Max Activating Token Index: 113

Text #2

Max Range: 1.8269. Min Range: -1.8269

Max Act: 1.6469. Min Act: -0.0000

Data Index: 548719 (C4 (Web Text))

Max Activating Token Index: 304

Text #3

Max Range: 1.8269. Min Range: -1.8269

Max Act: 1.4667. Min Act: -0.0000

Data Index: 294105 (C4 (Web Text))

Max Activating Token Index: 614

Text #4

Max Range: 1.8269. Min Range: -1.8269

Max Act: 1.4327. Min Act: -0.0000

Data Index: 315105 (C4 (Web Text))

Max Activating Token Index: 355

Text #5

Max Range: 1.8269. Min Range: -1.8269

Max Act: 1.4146. Min Act: -0.0000

Data Index: 302175 (C4 (Web Text))

Max Activating Token Index: 304

Text #6

Max Range: 1.8269. Min Range: -1.8269

Max Act: 1.4768. Min Act: -0.0000

Data Index: 326572 (C4 (Web Text))

Max Activating Token Index: 990

Text #7

Max Range: 1.8269. Min Range: -1.8269

Max Act: 1.4758. Min Act: -0.0000

Data Index: 334722 (C4 (Web Text))

Max Activating Token Index: 733

Text #8

Max Range: 1.8269. Min Range: -1.8269

Max Act: 1.3725. Min Act: -0.0000

Data Index: 1248919 (C4 (Web Text))

Max Activating Token Index: 484

Text #9

Max Range: 1.8269. Min Range: -1.8269

Max Act: 1.4844. Min Act: -0.0000

Data Index: 1069143 (C4 (Web Text))

Max Activating Token Index: 809

Text #10

Max Range: 1.8269. Min Range: -1.8269

Max Act: 1.3882. Min Act: -0.0000

Data Index: 785375 (C4 (Web Text))

Max Activating Token Index: 697

Text #11

Max Range: 1.8269. Min Range: -1.8269

Max Act: 1.3751. Min Act: -0.0000

Data Index: 1019422 (C4 (Web Text))

Max Activating Token Index: 588

Text #12

Max Range: 1.8269. Min Range: -1.8269

Max Act: 1.4539. Min Act: -0.0000

Data Index: 449956 (C4 (Web Text))

Max Activating Token Index: 60

Text #13

Max Range: 1.8269. Min Range: -1.8269

Max Act: 1.3369. Min Act: -0.0000

Data Index: 416941 (C4 (Web Text))

Max Activating Token Index: 718

Text #14

Max Range: 1.8269. Min Range: -1.8269

Max Act: 1.2523. Min Act: -0.0000

Data Index: 266645 (C4 (Web Text))

Max Activating Token Index: 198

Text #15

Max Range: 1.8269. Min Range: -1.8269

Max Act: 1.3225. Min Act: -0.0000

Data Index: 1151770 (C4 (Web Text))

Max Activating Token Index: 708

Text #16

Max Range: 1.8269. Min Range: -1.8269

Max Act: 1.3163. Min Act: -0.0000

Data Index: 461604 (C4 (Web Text))

Max Activating Token Index: 135

Text #17

Max Range: 1.8269. Min Range: -1.8269

Max Act: 1.2467. Min Act: -0.0000

Data Index: 814771 (C4 (Web Text))

Max Activating Token Index: 613

Text #18

Max Range: 1.8269. Min Range: -1.8269

Max Act: 1.2996. Min Act: -0.0000

Data Index: 459746 (C4 (Web Text))

Max Activating Token Index: 150

Text #19

Max Range: 1.8269. Min Range: -1.8269

Max Act: 1.3574. Min Act: -0.0000

Data Index: 141411 (C4 (Web Text))

Max Activating Token Index: 245